INDEX

Explanations

references to the media

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.73

ритори

-0.73

IntoConstraints

-0.70

BufferException

-0.65

êtres

-0.60

 JSONException

-0.59

 CONTRIBUTORS

-0.59

ținut

-0.59

URLException

-0.56

 veille

-0.56

POSITIVE LOGITS

 medium

0.72

Media

0.69

 />';

0.68

 media

0.68

'>

0.66

">

0.64

'])

0.64

"]);

0.64

media

0.63

"],

0.63

Activations Density 0.138%

references to the media

No Comments

No Known Activations